Refactor NYCInfoHubScraper to accept base_dir parameter; update main.py to pass script directory for improved data directory management

Author: dylanpicart

setup.py

@@ -2,7 +2,7 @@
 
 setup(
     name="nyc_infohub_excel_api_access",
-    version="1.0.12",
+    version="1.0.13",
     author="Dylan Picart",
     author_email="dylanpicart@mail.adelphi.edu",
     description="A Python scraper for downloading Excel datasets from NYC InfoHub.",

src/excel_scraper/main.py

@@ -14,7 +14,8 @@ async def main():
     Main entry point for running the NYCInfoHubScraper.
     Delegates the entire scraping workflow to the scraper's scrape_data().
     """
-    scraper = NYCInfoHubScraper()
+    script_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+    scraper = NYCInfoHubScraper(base_dir=script_dir)
     try:
         # The new refactored pipeline is entirely within scrape_data()
         await scraper.scrape_data()

src/excel_scraper/scraper.py

@@ -377,10 +377,10 @@ class NYCInfoHubScraper(BaseScraper):
     }
 
     def __init__(self, base_dir=None, data_dir=None, hash_dir=None, log_dir=None, skip_win_scan=True):
-        super().__init__(security_manager=SecurityManager("/var/run/clamav/clamd.ctl", skip_windows_scan=skip_win_scan), base_dir=base_dir)
-
         script_dir = os.path.abspath(os.path.dirname(__file__)) if "__file__" in globals() else os.getcwd()
         self._base_dir = base_dir or os.path.join(script_dir, "..")
+        super().__init__(security_manager=SecurityManager("/var/run/clamav/clamd.ctl", skip_windows_scan=skip_win_scan), base_dir=self._base_dir)
+
         self._data_dir = data_dir or os.path.join(self._base_dir, "data")
         self._hash_dir = hash_dir or os.path.join(self._base_dir, "hashes")
         self._log_dir = log_dir or os.path.join(self._base_dir, "logs")